CN111339846B

CN111339846B - Image recognition method and device, electronic equipment and storage medium

Info

Publication number: CN111339846B
Application number: CN202010089651.8A
Authority: CN
Inventors: 杨钰鑫; 惠维; 朱铖恺; 武伟; 李江涛
Original assignee: Shenzhen Sensetime Technology Co Ltd
Current assignee: Shenzhen Sensetime Technology Co Ltd
Priority date: 2020-02-12
Filing date: 2020-02-12
Publication date: 2022-08-12
Anticipated expiration: 2040-02-12
Also published as: JP2022522596A; TW202131219A; US20210312214A1; CN111339846A; SG11202106622XA; WO2021159594A1

Abstract

The present disclosure relates to an image recognition method and apparatus, an electronic device, and a storage medium, the method including: performing key point detection on an image to be processed, and determining a plurality of contour key point information of a target area in the image to be processed; correcting a target area in the image to be processed according to the plurality of contour key point information to obtain area image information of a correction area corresponding to the target area; and identifying the area image information to obtain an identification result of the target area. The target identification method and the target identification device can improve the accuracy of target identification.

Description

Image recognition method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to an image recognition method and apparatus, an electronic device, and a storage medium.

Background

In the fields of computer vision, intelligent video monitoring and the like, various targets (such as pedestrians, vehicles and the like) in an image need to be detected and identified. Under the scene that the license plate needs to be detected and identified (such as intelligent transportation, a vehicle monitoring system, a parking lot, vehicle heavy identification, fake-licensed vehicle identification and the like), the license plate may be distorted, rotated, perspective and deformed due to the fact that the vehicle speed is fast and the license plate may not face the collecting device, and the processing mode of the related art cannot rapidly identify the license plate and meanwhile guarantees high accuracy.

Disclosure of Invention

The present disclosure provides an image recognition technical solution.

According to an aspect of the present disclosure, there is provided an image recognition method including: performing key point detection on an image to be processed, and determining a plurality of contour key point information of a target area in the image to be processed; correcting a target area in the image to be processed according to the plurality of contour key point information to obtain area image information of a correction area corresponding to the target area; and identifying the area image information to obtain an identification result of the target area.

In a possible implementation manner, the performing keypoint detection on the image to be processed and determining information of a plurality of contour keypoints in a target region in the image to be processed includes: extracting and fusing the features of the image to be processed to obtain a feature map of the image to be processed; and carrying out key point detection on the feature map of the image to be processed to obtain a plurality of contour key point information of the target area in the image to be processed.

In a possible implementation manner, the step of correcting the target area in the image to be processed according to the information of the plurality of contour key points to obtain area image information of a corrected area corresponding to the target area includes: determining a homography transformation matrix between the target area and the correction area according to the first positions of the plurality of contour key points and the second position of the correction area; and correcting the image or the characteristic of the target area according to the homography transformation matrix to obtain the area image information of the correction area.

In one possible implementation manner, the determining a homographic transformation matrix between the target region and the correction region according to the first positions of the plurality of contour key points and the second position of the correction region includes: respectively carrying out normalization processing on the first position and the second position to obtain a normalized first position and a normalized second position; and determining a homography transformation matrix between the target area and the correction area according to the normalized first position and the normalized second position.

In a possible implementation manner, the correcting the image of the target area according to the homographic transformation matrix to obtain the area image information of the corrected area includes: determining pixel points corresponding to the third positions in the target area according to the third positions of the target points in the correction area and the homography transformation matrix; and mapping the pixel information of the pixel points corresponding to the third positions to the target points, and performing interpolation processing between the target points to obtain regional image information of the correction region.

In a possible implementation manner, the recognizing the area image information to obtain a recognition result of the target area includes: performing feature extraction on the region image information to obtain a feature vector of the region image information; and decoding the characteristic vector to obtain the identification result of the target area.

In a possible implementation manner, the method is implemented by a neural network, where the neural network includes a target detection network, a correction network, and an identification network, the target detection network is used to perform key point detection on the image to be processed, the correction network is used to correct the target area, and the identification network is used to identify the area image information, where the method further includes:

training the target detection network according to a preset training set to obtain the trained target detection network, wherein the training set comprises a plurality of sample images, and contour key point marking information, background marking information and category marking information of a target area in each sample image; and training the correction network and the recognition network according to the training set and the trained target detection network.

In a possible implementation manner, the training of the target detection network according to a preset training set to obtain a trained target detection network includes:

performing feature extraction on the sample image through the feature extraction sub-network to obtain a first feature of the sample image; performing feature fusion on the first feature through the feature fusion sub-network to obtain a fusion feature of the sample image; detecting the fusion characteristics through the detection sub-network to obtain contour key point detection information and background detection information of the target in the sample image; and training the target detection network according to the contour key point detection information and the background detection information of the plurality of sample images and the contour key point labeling information and the background labeling information of the plurality of sample images to obtain the trained target detection network.

In a possible implementation manner, the target region includes a license plate region of a vehicle, and the recognition result of the target region includes a character category of the license plate region.

According to an aspect of the present disclosure, there is provided an image recognition apparatus including: the system comprises a key point detection module, a key point detection module and a processing module, wherein the key point detection module is used for detecting key points of an image to be processed and determining a plurality of contour key point information of a target area in the image to be processed; the correction module is used for correcting a target area in the image to be processed according to the plurality of contour key point information to obtain area image information of a correction area corresponding to the target area; and the identification module is used for identifying the area image information to obtain an identification result of the target area.

In one possible implementation, the key point detecting module includes: the feature extraction and fusion submodule is used for extracting and fusing features of the image to be processed to obtain a feature map of the image to be processed; and the detection submodule is used for detecting key points of the characteristic diagram of the image to be processed to obtain a plurality of contour key point information of a target area in the image to be processed.

In one possible implementation, the plurality of contour keypoint information includes a first position of the plurality of contour keypoints, and the correction module includes: the transformation matrix determining submodule is used for determining a homography transformation matrix between the target area and the correction area according to the first positions of the contour key points and the second position of the correction area; and the correction submodule is used for correcting the image or the characteristic of the target area according to the homography transformation matrix to obtain the area image information of the correction area.

In one possible implementation, the transformation matrix determining submodule is configured to: respectively carrying out normalization processing on the first position and the second position to obtain a normalized first position and a normalized second position; and determining a homography transformation matrix between the target area and the correction area according to the normalized first position and the normalized second position.

In one possible implementation, the syndrome module is configured to: determining pixel points corresponding to the third positions in the target area according to the third positions of the target points in the correction area and the homography transformation matrix; and mapping the pixel information of the pixel point corresponding to each third position to each target point, and performing interpolation processing between the target points to obtain the regional image information of the correction region.

In one possible implementation, the identification module includes: extracting the characteristics of the regional image information to obtain a characteristic vector of the regional image information; and decoding the characteristic vector to obtain the identification result of the target area.

In a possible implementation manner, the apparatus is implemented by a neural network, where the neural network includes a target detection network, a correction network, and an identification network, the target detection network is used to perform key point detection on the image to be processed, the correction network is used to correct the target area, and the identification network is used to identify the area image information, where the apparatus further includes:

the first training module is used for training the target detection network according to a preset training set to obtain the trained target detection network, wherein the training set comprises a plurality of sample images, and contour key point marking information, background marking information and category marking information of a target area in each sample image; and the second training module is used for training the correction network and the recognition network according to the training set and the trained target detection network.

In one possible implementation manner, the target detection network includes a feature extraction sub-network, a feature fusion sub-network, and a detection sub-network, and the first training module is configured to: performing feature extraction on the sample image through the feature extraction sub-network to obtain a first feature of the sample image; performing feature fusion on the first feature through the feature fusion sub-network to obtain a fusion feature of the sample image; detecting the fusion characteristics through the detection sub-network to obtain contour key point detection information and background detection information of the target in the sample image; and training the target detection network according to the contour key point detection information and the background detection information of the plurality of sample images and the contour key point marking information and the background marking information of the plurality of sample images to obtain the trained target detection network.

According to an aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.

According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.

According to the embodiment of the disclosure, the information of a plurality of contour key points of the target area in the image to be processed can be determined, the target area is corrected according to the information of the plurality of contour key points, the corrected image information of the area is recognized, the recognition result of the target area is obtained, and therefore the accuracy of target recognition is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

Fig. 1 shows a flow chart of an image recognition method according to an embodiment of the present disclosure.

Fig. 2 shows a schematic diagram of a keypoint detection process according to an embodiment of the present disclosure.

Fig. 3 shows a schematic diagram of an image recognition process according to an embodiment of the present disclosure.

Fig. 4 illustrates a block diagram of an image recognition apparatus according to an embodiment of the present disclosure.

Fig. 5 shows a block diagram of an electronic device according to an embodiment of the disclosure.

Fig. 6 illustrates a block diagram of an electronic device in accordance with an embodiment of the disclosure.

Detailed Description

Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.

Fig. 1 shows a flowchart of an image recognition method according to an embodiment of the present disclosure, as shown in fig. 1, the method including:

in step S11, performing keypoint detection on an image to be processed, and determining a plurality of contour keypoint information of a target region in the image to be processed;

in step S12, according to the plurality of contour key point information, correcting a target area in the image to be processed to obtain area image information of a correction area corresponding to the target area;

in step S13, the area image information is recognized, and a recognition result of the target area is obtained.

In one possible implementation, the image recognition method may be performed by an electronic device such as a terminal device or a server, the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or the like, and the method may be implemented by a processor calling a computer readable instruction stored in a memory. Alternatively, the method may be performed by a server.

For example, the image to be processed may be an image or a video frame acquired by an image acquisition device (e.g., a camera), and the like, and the image to be processed includes an object to be recognized, such as a pedestrian, a vehicle, a license plate, and the like.

In one possible implementation, in step S11, keypoint detection may be performed on the image to be processed, and a plurality of contour keypoint information on the contour of an image region (which may be referred to as a target region) where the target is located in the image to be processed is determined. In the case where the target region is a quadrangular region, the plurality of contour key points of the target region may be, for example, four vertices of the target region. It should be understood that the number of detected contour keypoints can be set by one skilled in the art according to actual situations, as long as the detected contour keypoints can define the range of the target area, and the specific shape of the target area and the number of contour keypoints are not limited by the disclosure.

In one possible implementation, due to the shooting angle problem of the image to be processed, the target area in the image to be processed may be distorted, rotated, deformed, and the like. In this case, in step S12, the target region in the image to be processed may be corrected based on the plurality of contour key point information, for example, by homography conversion, to obtain region image information of the correction region corresponding to the target region. The correction area is an area displayed when the target area is viewed positively, for example, when the target is a license plate, the correction area is a rectangular area where the license plate is located when the license plate is viewed positively. The area image information of the correction area may be an image or a feature map of the correction area.

In one possible implementation, after obtaining the area image information, the area image information may be identified in step S13 to obtain an identification result of the target area. The region image information may be subjected to feature extraction, for example, by a neural network, and the extracted features may be decoded to obtain the recognition result.

In one possible implementation manner, the target region includes a license plate region of the vehicle, and the recognition result of the target region includes a character category of the license plate region. That is, when the target to be recognized is the license plate of the vehicle, a plurality of contour key points (for example, 4 vertices) of the license plate region in the image can be detected, and then the license plate region is corrected and recognized to obtain the character type of the license plate region, for example, the license plate region includes the characters 9815 QW.

In one possible implementation manner, when the target to be recognized is a billboard or a shop signboard, etc., the obtained recognition result of the target area is characters and/or numbers on the billboard or the shop signboard; and when the target to be identified is the traffic marker, the obtained identification result of the target area is the marker type of the traffic marker. The present disclosure is not so limited.

In one possible implementation, step S11 may include:

extracting and fusing the features of the image to be processed to obtain a feature map of the image to be processed;

and carrying out key point detection on the feature map of the image to be processed to obtain a plurality of contour key point information of the target area in the image to be processed.

For example, the keypoint detection of the image to be processed may be achieved by a target detection network, which may be, for example, a convolutional neural network. The target detection network may include a feature extraction sub-network, a feature fusion sub-network, and a detection sub-network.

In a possible implementation manner, the feature extraction may be performed on the image to be processed through the feature extraction sub-network, so as to obtain features of multiple scales of the image to be processed. The feature extraction sub-network may employ a residual network Resnet, comprising a plurality of residual layers or blocks. It should be understood that the feature extraction sub-network may also adopt network structures such as ***net (*** network), vgnet (vgg network), shuffnet (shuffle network), and dark network, and the present disclosure does not limit this.

In a possible implementation manner, the features of multiple scales of the image to be processed are fused through the feature fusion sub-network to obtain the feature of one scale, that is, the feature map of the image to be processed. The feature fusion sub-network may adopt a feature pyramid network FPN, and may also adopt network structures such as NAS-FPN (auto-search feature pyramid network), hourglass (hourglass network), and the like, which is not limited in this disclosure.

In a possible implementation manner, the detection subnetwork can perform key point detection on the feature map of the image to be processed to obtain a plurality of contour key point information of the target area in the image to be processed. The detection subnetwork may include a plurality of convolution layers and a plurality of detection layers (e.g., including a fully connected layer), further extract feature information in a feature map of the image to be processed by the plurality of convolution layers, and then respectively detect positions of key points in the feature information by the plurality of detection layers. In the case where the target area is a quadrangle, 4 positioning thermodynamic diagrams can be predicted, and the positions of the top left vertex, the top right vertex, the bottom right vertex and the bottom left vertex (i.e., 4 key points) of the target area are respectively positioned. Each thermodynamic diagram can be defined as the vertex coordinates are located at 1, the rest are 0, 01 coding can be selected, or gaussian coding can be substituted, and the disclosure does not limit this.

Fig. 2 shows a schematic diagram of a keypoint detection process according to an embodiment of the present disclosure. As shown in fig. 2, the image 21 to be processed may be input into the target detection network, and feature extraction and fusion are performed sequentially through the residual error network (Res)22 and the Feature Pyramid Network (FPN)23 to obtain a feature map 24. The size of the image 21 to be processed may be, for example, 320 × 280, and after feature extraction and fusion, the feature map 24 with the size of 80 × 70 × 64 is obtained; the feature map 24 is further convolved and keypoint detected by a detection sub-network (not shown) to obtain a 80 × 70 × 4 localization thermodynamic diagram of the four keypoints, thereby determining the positions of the top left, top right, bottom right, and bottom left vertices of the target region.

By the method, the information of the plurality of contour key points of the target area can be quickly determined, so that the boundary contour of the target area is accurately defined, and the processing speed and the processing precision are improved.

In one possible implementation manner, the plurality of contour keypoint information includes first positions of the plurality of contour keypoints, and step S12 may include:

determining a homography transformation matrix between the target area and the correction area according to the first positions of the plurality of contour key points and the second position of the correction area;

and correcting the image or the characteristic of the target area according to the homography transformation matrix to obtain the area image information of the correction area.

For example, after determining a plurality of contour keypoint information of the target region, a correction may be made to the target region. The plurality of contour keypoint information may include position coordinates of each contour keypoint in the image to be processed or the feature map of the image to be processed (i.e., a first position of each contour keypoint). When the target area is a quadrilateral area, 4 contour key points can be included.

In one possible implementation, the scale of the image to be processed or the feature map thereof may be h (height) × w (width) × C (number of channels), the coordinates of the contour key points are (x1, y1, x2, y2, x3, y3, x4, y4), and the corrected area is h _H (height). times.w _H (width) × C (number of channels). The position of the target area can be determined according to the first positions of the plurality of contour key points, and then the homography transformation matrix between the target area and the correction area can be determined according to the position of the target area and the second position of the correction area. It should be understood that the homographic transformation matrix between the target region and the correction region may be determined in a manner known in the art, and the present disclosure is not limited thereto.

In a possible implementation manner, the step of determining a homographic transformation matrix between the target region and the correction region according to the first positions of the contour keypoints and the second position of the correction region may include:

respectively carrying out normalization processing on the first position and the second position to obtain a normalized first position and a normalized second position;

and determining a homography transformation matrix between the target area and the correction area according to the normalized first position and the normalized second position.

That is, the input contour keypoint coordinates (x1, y1, x2, y2, x3, y3, x4, y4), and the output correction area h may be corrected _H (height). times.w _H The coordinates of (width) × C (number of channels) are normalized respectively, and the input coordinates and the output coordinates are normalized to [ -1,1]And obtaining the normalized first position and the normalized second position. According to the normalized first position and the normalized second position, a homography transformation matrix between the normalized target region and the correction region is determined (for example, a 3 × 3 matrix is obtained), and the determination manner of the homography transformation matrix is not limited in the present disclosure.

By the method, the scales of the target area and the correction area can be unified, errors caused by the scale difference of the target area and the correction area are avoided, and the accuracy of the homography transformation matrix is improved.

In a possible implementation manner, the step of correcting the image or the feature of the target area according to the homographic transformation matrix to obtain the area image information of the corrected area may include:

determining pixel points corresponding to the third positions in the target area according to the third positions of the target points in the correction area and the homography transformation matrix;

and mapping the pixel information of the pixel points corresponding to the third positions to the target points, and performing interpolation processing between the target points to obtain regional image information of the correction region.

For example, the normalized second position for the correction area may be [ -1,1 ] on the x-axis and y-axis coordinates]Respectively take w at equal intervals _H And h _H Points to obtain rasterized coordinates (total h) of the corrected region _H ×w _H Individual coordinates) with rasterized coordinates as correction regionsA plurality of target points in the domain. And calculating the positions of the corresponding pixel points in the target area according to the third positions of the target points and the homography transformation matrix, thereby determining the pixel points corresponding to the third positions in the target area.

In a possible implementation manner, the pixel information (i.e., pixel values) of the pixel points corresponding to the third positions may be mapped to the target points, and interpolation processing may be performed between the target points to obtain area image information of the correction area. The bilinear interpolation may be used, and other interpolation methods may also be used, which is not limited by this disclosure. The area image information may be an area image or an area feature map, which is not limited by the present disclosure.

In this way, the tilt-rotated target area can be corrected to the horizontal direction. This process, which may be referred to as a homography pooling (Homopooling) operation, differentiates and backproplates the images or features used to correct the target region, and may be embedded in any neural network for end-to-end training, thereby enabling the entire image recognition process to be implemented in a unified network.

In one possible implementation, step S13 includes:

extracting the characteristics of the regional image information to obtain a characteristic vector of the regional image information; and decoding the characteristic vector to obtain the identification result of the target area.

For example, the region image information may be identified by an identification network, which may include network layers such as a plurality of convolutional layers, a group regularization (group regularization) layer, a RELU activation layer, and a max pooling layer. By extracting the features of the region image information through each network layer, a feature vector having a width of 1, for example, a feature vector having a size of 1 × 47 can be obtained.

In a possible implementation, the identification network may further include a full connection layer and a CTC (connection time Classification) decoder. Processing the feature vectors through the full-connection layer to obtain character probability distribution vectors of the regional image information; the recognition result of the target region can be obtained by decoding the character probability distribution vector through a CTC decoder. When the target is a license plate, the recognition result of the target area is a character corresponding to the license plate, such as a character 9815 QW. In this way, the accuracy of the recognition result can be improved.

Fig. 3 shows a schematic diagram of an image recognition process according to an embodiment of the present disclosure. As shown in fig. 3, the image recognition method according to the embodiment of the present disclosure may be implemented by a neural network, where the neural network includes a target detection network 31, a correction network 32, and an identification network 33, the target detection network 31 is used to perform keypoint detection on the image to be processed, the correction network 32 is used to correct the target area, and the identification network 33 is used to identify the area image information.

As shown in fig. 3, the target in the image to be processed 34 is a license plate of a vehicle, and the image to be processed 34 may be input to the target detection network 31 for performing key point detection, so as to obtain an image 35 including four vertices of the license plate; correcting the license plate area of the image to be processed 34 by four vertexes in the image 35 through a correction network 32 to obtain a license plate image 36; the license plate image 36 is input into the recognition network 33 for recognition, and a recognition result 37 of the license plate region is obtained, namely, the characters 9815QW corresponding to the license plate.

Before deploying the neural network, the neural network needs to be trained. The image recognition method according to the embodiment of the present disclosure further includes:

training the target detection network according to a preset training set to obtain the trained target detection network, wherein the training set comprises a plurality of sample images, outline key point marking information, background marking information and category marking information of a target area in each sample image;

and training the correction network and the recognition network according to the training set and the trained target detection network.

For example, the neural network may be trained in two stages, i.e., the target detection network is trained first, and then the correction network and the recognition network are trained.

In the first stage of training, the sample images in the training set can be input into a target detection network, and outline key point detection information of a target area in the sample images is output; and adjusting parameters of the target detection network according to the difference between the contour key point detection information and the contour key point marking information of the plurality of sample images until a preset training condition is met, so as to obtain the trained target detection network.

In the second stage of training, the sample images in the training set can be input into the trained target detection network, and the training identification result of the target area in the sample images is obtained through the processing of the trained target detection network, the trained correction network and the trained identification network; and adjusting parameters of the correction network and the recognition network according to the difference between the training recognition results and the class marking information of the plurality of sample images until a preset training condition is met, so as to obtain the trained correction network and the trained recognition network.

By the mode, the training effect can be improved, and the training speed is accelerated.

In a possible implementation manner, the training the target detection network according to a preset training set, and the step of obtaining the trained target detection network includes:

performing feature extraction on the sample image through the feature extraction sub-network to obtain a first feature of the sample image;

performing feature fusion on the first feature through the feature fusion sub-network to obtain a fusion feature of the sample image;

detecting the fusion characteristics through the detection sub-network to obtain contour key point detection information and background detection information of the target in the sample image;

and training the target detection network according to the contour key point detection information and the background detection information of the plurality of sample images and the contour key point marking information and the background marking information of the plurality of sample images to obtain the trained target detection network.

For example, detection of background may be added during training in order to improve the training effect. The sample image can be input into a feature extraction sub-network for feature extraction to obtain a first feature of the sample image; inputting the first features into a feature fusion sub-network for feature fusion to obtain fusion features of the sample image; and inputting the fusion characteristics into a detection sub-network for detection to obtain contour key point detection information and background detection information of the target in the sample image. That is, when the target is a license plate, detection information of four vertices and detection information of a background in the sample image can be obtained.

In a possible implementation manner, the network loss of the target detection network can be determined by the contour key point detection information and the background detection information of the plurality of sample images and the contour key point labeling information and the background labeling information of the plurality of sample images, so that the parameters of the target detection network are adjusted according to the network loss until the preset training condition is met, and the trained target detection network is obtained.

By adding background detection as a supervision signal, the training effect of the target detection network can be greatly improved.

According to the image recognition method disclosed by the embodiment of the disclosure, targets (such as license plates, advertising boards, traffic signs and the like) with multiple angles and indefinite word lengths in the images of the images can be accurately recognized. According to the method, key point identification is used for replacing the license plate detection based on the boundary frame, pixel-by-pixel regression is not needed, a detection anchor is not needed, non-maximum value inhibition is omitted, and the detection speed is greatly improved. And the thermodynamic diagram of the key points is used as a regression target, so that the positioning accuracy is improved. Meanwhile, more license plate information can be acquired by increasing the number of points and is used for correcting the license plate in a homography pooling manner.

According to the image recognition method disclosed by the embodiment of the disclosure, the license plate pictures or characteristics can be corrected by utilizing the homography pooling, and the images or characteristics can be embedded into any network, so that a unified network of end-to-end joint training is realized, all parts of the network can be jointly optimized, and the speed and the precision are ensured.

The image recognition method can be applied to scenes such as smart cities, intelligent transportation, security monitoring, parking lots, vehicle heavy recognition and fake-licensed vehicle recognition, the license plate number can be rapidly and accurately recognized, and then charging, fine payment, fake-licensed vehicle detection and the like can be carried out by utilizing the license plate number.

It is understood that the above-mentioned embodiments of the method of the present disclosure can be combined with each other to form a combined embodiment without departing from the principle logic, which is limited by the space, and the detailed description of the present disclosure is omitted. Those skilled in the art will appreciate that in the above methods of the specific embodiments, the specific order of execution of the steps should be determined by their function and possibly their inherent logic.

In addition, the present disclosure also provides an image recognition apparatus, an electronic device, a computer-readable storage medium, and a program, which can be used to implement any image recognition method provided by the present disclosure, and the corresponding technical solutions and descriptions and corresponding descriptions in the methods section are not repeated.

Fig. 4 shows a block diagram of an image recognition apparatus according to an embodiment of the present disclosure, as shown in fig. 4, the apparatus including:

the key point detection module 41 is configured to perform key point detection on an image to be processed, and determine a plurality of contour key point information of a target area in the image to be processed; a correcting module 42, configured to correct a target area in the image to be processed according to the plurality of contour key point information, so as to obtain area image information of a corrected area corresponding to the target area; and the identifying module 43 is configured to identify the area image information to obtain an identification result of the target area.

In a possible implementation manner, the apparatus is implemented by a neural network, where the neural network includes an object detection network, a correction network, and an identification network, the object detection network is configured to perform key point detection on the image to be processed, the correction network is configured to correct the target area, and the identification network is configured to identify the area image information, where the apparatus further includes:

In one possible implementation manner, the target detection network includes a feature extraction sub-network, a feature fusion sub-network, and a detection sub-network, and the first training module is configured to: performing feature extraction on the sample image through the feature extraction sub-network to obtain a first feature of the sample image; performing feature fusion on the first feature through the feature fusion sub-network to obtain a fusion feature of the sample image; detecting the fusion characteristics through the detection sub-network to obtain contour key point detection information and background detection information of the target in the sample image; and training the target detection network according to the contour key point detection information and the background detection information of the plurality of sample images and the contour key point labeling information and the background labeling information of the plurality of sample images to obtain the trained target detection network.

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.

Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a non-volatile computer readable storage medium.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.

The disclosed embodiments also provide a computer program product comprising computer readable code, which when run on a device, a processor in the device executes instructions for implementing the image recognition method provided in any of the above embodiments.

The embodiments of the present disclosure also provide another computer program product for storing computer readable instructions, which when executed cause a computer to perform the operations of the image recognition method provided in any one of the above embodiments.

The electronic device may be provided as a terminal, server, or other form of device.

Fig. 5 illustrates a block diagram of an electronic device 800 in accordance with an embodiment of the disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like terminal.

Referring to fig. 5, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium, such as the memory 804, is also provided that includes computer program instructions executable by the processor 820 of the electronic device 800 to perform the above-described methods.

Fig. 6 illustrates a block diagram of an electronic device 1900 in accordance with an embodiment of the disclosure. For example, electronic device 1900 may be provided as a server. Referring to fig. 6, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the electronic device 1900 to perform the above-described methods.

The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An image recognition method, comprising:

performing key point detection on an image to be processed, and determining a plurality of contour key point information of a target area in the image to be processed;

correcting a target area in the image to be processed according to the plurality of contour key point information to obtain area image information of a correction area corresponding to the target area;

identifying the area image information to obtain an identification result of the target area;

wherein the information of the contour key points includes first positions of the contour key points, and the correcting a target area in the image to be processed according to the information of the contour key points to obtain area image information of a corrected area corresponding to the target area includes:

2. The method according to claim 1, wherein the performing keypoint detection on the image to be processed and determining a plurality of contour keypoint information of the target region in the image to be processed comprises:

3. The method of claim 1, wherein determining a homographic transformation matrix between the target region and the correction region according to the first locations of the plurality of contour keypoints and the second location of the correction region comprises:

4. The method according to any one of claims 1 to 3, wherein the identifying the area image information to obtain the identification result of the target area comprises:

extracting the characteristics of the regional image information to obtain a characteristic vector of the regional image information;

and decoding the characteristic vector to obtain the identification result of the target area.

5. The method according to any one of claims 1-3, wherein the method is implemented by a neural network comprising an object detection network for performing keypoint detection on the image to be processed, a correction network for correcting the object region, and an identification network for identifying the region image information,

wherein the method further comprises:

6. The method of claim 5, wherein the target detection network comprises a feature extraction sub-network, a feature fusion sub-network, and a detection sub-network,

the training the target detection network according to a preset training set to obtain the trained target detection network comprises:

7. The method according to any one of claims 1 to 3, wherein the target region comprises a license plate region of a vehicle, and the recognition result of the target region comprises a character class of the license plate region.

8. An image recognition apparatus, characterized by comprising:

the system comprises a key point detection module, a key point detection module and a processing module, wherein the key point detection module is used for detecting key points of an image to be processed and determining a plurality of contour key point information of a target area in the image to be processed;

the correction module is used for correcting a target area in the image to be processed according to the plurality of contour key point information to obtain area image information of a correction area corresponding to the target area;

the identification module is used for identifying the area image information to obtain an identification result of the target area;

wherein the plurality of contour keypoint information comprises first locations of the plurality of contour keypoints, the correction module comprising:

the transformation matrix determining submodule is used for determining a homography transformation matrix between the target area and the correction area according to the first positions of the contour key points and the second position of the correction area;

the correction submodule is used for determining pixel points corresponding to the third positions in the target area according to the third positions of the target points in the correction area and the homography transformation matrix; and mapping the pixel information of the pixel points corresponding to the third positions to the target points, and performing interpolation processing between the target points to obtain regional image information of the correction region.

9. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the memory-stored instructions to perform the method of any of claims 1 to 7.

10. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1 to 7.